mx-finance-data

Financial data query

Scope of functions

1. Supported query object scope

• Stocks (A-shares, Hong Kong stocks, US stocks)
• Sectors, indices, shareholders
• Corporate issuers, bonds, unlisted companies
• Stock market, fund market, bond market

2. Supported query data types

Supports querying the following types of structured data:

• Real-time quotes(current price, price change, order book data, etc.)
• Quantitative data(technical indicators, capital flows, etc.)
• Statement data(revenue, net profit, financial ratios, etc.)

3. Supported query methods andstrict limits

Supports combined queries with multiple entities, multiple indicators, and multiple time ranges.Due to backend interface limitations, a single query must comply with the following quotas:

• Entity upper limit: a single query supports at most 5 stocks/financial entities.
• Processing logic: If a user request exceeds the above limit, the Skill will prioritize the first 5 entities and provide a notice in the result description file.

Example: "Query the revenue of six stocks A, B, C, D, E, and F" -> only the first five are returned.

4. Output results

After execution, the Skill outputs the following files:

• One query result xlsx file, used to carry the structured query results
• One result description txt file, used to describe the query content, meaning of the results, and necessary explanations

---

Query examples

Basic indicator query

• East Money's fundamentals
• Kweichow Moutai's operating revenue and net profit for the most recent year
• Performance of semiconductor ETFs

Real-time quotes and order book query

• Current real-time buy orders for 300059
• NVIDIA's current latest price and price change
• CSI 300's current level and turnover

Multi-entity, multi-indicator, multi-time query (note the quota)

• Compliant example: Compare the gains since the Spring Festival of the ChiNext Index, CSI 300, and CSI 500 (3 entities) (1 indicator).
• Compliant example: East Money and Pinduoduo (2 entities)'s revenue, gross profit, and net profit for the most recent year (3 indicators).
• Over-limit notice: If querying the "PE of the top ten weighted stocks in Shanghai and Shenzhen," the system will take the top 5 for the query.

---

Supplementary notes

• This Skill is oriented toward financial structured data and relational data queries, and does not focus on subjective analysis, investment advice, or news interpretation.
• The statement must contain explicit financial entity names.
• When users initiate queries in natural language, the Skill can identify the query objects, indicators, and time ranges based on the question content, and output structured result files.
• For query requests within the supported scope, prioritize outputting structured query results and simultaneously generate a result explanation file for subsequent use.

3. Install dependencies

pip3 install httpx pandas openpyxl --user

Quick start

Execute in the working directory

python3 {baseDir}/scripts/get_data.py --query "贵州茅台近期走势如何"

Output example

xlsx: /path/to/miaoxiang/mx_finance_data/mx_finance_data_9535fe18.xlsx
描述: /path/to/miaoxiang/mx_finance_data/mx_finance_data_9535fe18_description.txt
行数: 42

Output file description

File	Description
mx_finance_data_<查询id>.xlsx	Structured data table containing the requested entities and metrics
mx_finance_data_<查询id>_description.txt	Includes query logic description, field meanings, andquota truncation notice